Early diagnosis of retinoblastoma in the current clinical practice remains challenging due to the lack of access to timely and accurate eye examinations, which are essential as late stages of retinoblastoma often lead to enucleation and blindness. To address this issue, I developed RetinAI, a low-cost wearable device that uses artificial intelligence to look for early signs of retinoblastoma. The system can detect a white glow in the pupil and also take images inside the eye to look for tumors without any pupil-dilating medication. In testing, RetinAI demonstrated high accuracy in detecting retinoblastoma. RetinAI can significantly improve RB early detection and be used at home or in small clinics without eye specialists, especially in underserved communities.